from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.pipeline import Pipeline
from sklearn.naive_bayes import MultinomialNB
from sklearn import metrics

# 1 ______________ PIPELINE (tf-idf vectorizer -> classifier)
text_clf = Pipeline([('tfidf', TfidfVectorizer()),('clf', MultinomialNB())])

# 2 APPRENTISSAGE on donne les questions et les rponses
text_clf.fit(text_train, outcome_train)

# 3 TEST sur donnes non vues durant phase apprentissage
predicted = text_clf.predict(text_test)
# verification des predictions 
print(metrics.accuracy_score(outcome_test , predicted))
 